Instructions to use aitf-komdigi/KomdigiITS-3B-PADClassification-Merged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aitf-komdigi/KomdigiITS-3B-PADClassification-Merged with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="aitf-komdigi/KomdigiITS-3B-PADClassification-Merged")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("aitf-komdigi/KomdigiITS-3B-PADClassification-Merged")
model = AutoModelForMultimodalLM.from_pretrained("aitf-komdigi/KomdigiITS-3B-PADClassification-Merged")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use aitf-komdigi/KomdigiITS-3B-PADClassification-Merged with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aitf-komdigi/KomdigiITS-3B-PADClassification-Merged"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aitf-komdigi/KomdigiITS-3B-PADClassification-Merged",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/aitf-komdigi/KomdigiITS-3B-PADClassification-Merged

SGLang

How to use aitf-komdigi/KomdigiITS-3B-PADClassification-Merged with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "aitf-komdigi/KomdigiITS-3B-PADClassification-Merged" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aitf-komdigi/KomdigiITS-3B-PADClassification-Merged",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "aitf-komdigi/KomdigiITS-3B-PADClassification-Merged" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aitf-komdigi/KomdigiITS-3B-PADClassification-Merged",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use aitf-komdigi/KomdigiITS-3B-PADClassification-Merged with Docker Model Runner:
```
docker model run hf.co/aitf-komdigi/KomdigiITS-3B-PADClassification-Merged
```

KomdigiITS-3B-PADClassification-Merged

Fine-tuning dari: aitf-komdigi/KomdigiITS-3B-PAD-CPT

Model ini digunakan untuk klasifikasi kategori usia dari berbagai konten media sosial

Training

LoRA Rank: 16
LoRA Alpha: 32
Epoch: 1
LR: 2e-05
Max seq length: 2048

Dataset

Text Classification Rating Usia (7+, 13+, 15+, 18+, Semua Umur,Konten Terlarang, Unrated)
Keyword Extraction
Multimodal Classification Rating Usia (7+, 13+, 15+, 18+, Semua Umur,Konten Terlarang, Unrated)

TOTAL DATASET

Train Samples: 54003
Validation Samples: 6754
Testing Samples : 6749

LABEL KATEGORI USIA:

7+
13+
15+
18+
Semua Umur
Konten Terlarang
Unrated

Downloads last month: 41

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for aitf-komdigi/KomdigiITS-3B-PADClassification-Merged

Base model

mistralai/Ministral-3-3B-Base-2512

Finetuned

aitf-komdigi/KomdigiITS-3B-PAD-CPT

Adapter

(3)

this model